Bayesian optimization algorithms for accelerator physics

R Roussel, AL Edelen, T Boltz, D Kennedy… - … review accelerators and …, 2024 - APS
Accelerator physics relies on numerical algorithms to solve optimization problems in online
accelerator control and tasks such as experimental design and model calibration in …

Large language models for human-machine collaborative particle accelerator tuning through natural language

J Kaiser, A Lauscher, A Eichler - Science Advances, 2025 - science.org
Autonomous tuning of particle accelerators is an active and challenging research field with
the goal of enabling advanced accelerator technologies and cutting-edge high-impact …

Learning to do or learning while doing: Reinforcement learning and bayesian optimisation for online continuous tuning

J Kaiser, C Xu, A Eichler, AS Garcia, O Stein… - arXiv preprint arXiv …, 2023 - arxiv.org
Online tuning of real-world plants is a complex optimisation problem that continues to
require manual intervention by experienced human operators. Autonomous tuning is a …

Bridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations

J Kaiser, C Xu, A Eichler, A Santamaria Garcia - Physical Review Accelerators …, 2024 - APS
Machine learning has emerged as a powerful solution to the modern challenges in
accelerator physics. However, the limited availability of beam time, the computational cost of …

[PDF][PDF] Optimisation of the Touschek Lifetime in Synchrotron Light Sources Using Badger

S Liuzzo, N Carmignani, L Carver, L Hoummi… - JACoW …, 2023 - epaper.kek.jp
Badger [1] is a software designed to easily access several optimizers (simplex, RCDS [2],
Bayesian optimization, etc.) to solve a given multidimensional minimization/maximization …

Towards Agentic AI on Particle Accelerators

A Sulc, T Hellert, R Kammering, H Houscher… - arXiv preprint arXiv …, 2024 - arxiv.org
As particle accelerators grow in complexity, traditional control methods face increasing
challenges in achieving optimal performance. This paper envisions a paradigm shift: a …

[PDF][PDF] Bayesian Optimization for SASE Tuning at the European XFEL

C Xu, E Bründermann, AS Müller, AS Garcia - Pulse, 2023 - cr-xu.github.io
Parameter tuning is a regular task and takes considerable time for daily operations at FEL
facilities. In this contribution, we demonstrate SASE pulse energy optimization at the …

[PDF][PDF] How can machine learning help future light sources?

AS Garcia, C Xu, L Scomparin, E Bründermann… - Proc. FLS'23 - epaper.kek.jp
Abstract Machine learning (ML) is one of the key technologies that can considerably extend
and advance the capabilities of particle accelerators and needs to be included in their future …

[PDF][PDF] Integration of an Optimizer Framework into the Control System at KARA

C Xu, E Blomley, AS Garcia, AS Müller… - … , Cape Town, South …, 2023 - inspirehep.net
Tuning particle accelerators is not straightforward as they depend on a large number of non-
linearly correlated parameters that drift over time. In recent years advanced numerical …

[PDF][PDF] Vertical beam halo characterisation at the ESRF EBS for operation with reduced in vacuum undulator gap

N Carmignani, LR Carver, G Le Bec, SM Liuzzo… - Proc. IPAC'24 - jacow.org
The vertical beam halo is the main limitation for very low gap operation of in-vacuum
undulators at the ESRF EBS. The vertical halo is due to Touschek electrons with large …